AI-powered MRI analysis offers automated risk stratification via body composition in multiple myeloma patients.
Key Details
- 1A deep-learning system was trained and validated on 39 whole-body MRI scans in multiple myeloma patients.
- 2The pipeline enables automated tissue and organ segmentation in seconds or minutes, speeding up analysis and reducing operator time.
- 3Longitudinal MRI analysis revealed that decreases in skeletal muscle and increases in fatty tissue during treatment are statistically significant (p < 0.001).
- 4Higher baseline subcutaneous adipose tissue predicted better progression-free survival (HR = 0.60–0.67), while increases in visceral fat correlated with worse survival (HR = 2.89).
- 5Including body composition metrics in routine MRI adds no burden but may facilitate earlier interventions and better patient outcomes.
Why It Matters
This work highlights how AI can transform standard imaging into a biomarker-rich tool that informs prognosis and individualized care in oncology, maximizing existing imaging data without added patient risk or discomfort.
Source
AuntMinnie
Related News
•Radiology Business
FDA Approves SimBioSys AI Tool for Breast Cancer Risk via MRI
SimBioSys received FDA clearance for TumorSight Risk, an AI tool assessing breast cancer recurrence risk using MRI.
•AuntMinnie
LLMs Rarely Recommend Unnecessary Imaging, Except for Thyroid Ultrasound
Large language models seldom over-recommend imaging, but thyroid ultrasound guidance shows substantial discrepancies.
•Radiology Business
UC Irvine Implements AI to Find Lung Cancer Screening Candidates
UC Irvine's radiology department developed an NLP tool to identify patients eligible for lung cancer screening from EHR notes.